Multi-hop Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
1.31Average Running Time (s)
6
Feb 26, 2026
0.91Latency (s)
6
Feb 26, 2026
0.63Avg Running Time (s)
6
Feb 26, 2026
84.8Answer Rate
6
Feb 26, 2026
0.75Ans Rate
6
Feb 26, 2026
38.76EM
6
Feb 26, 2026
39.7EM
6
Feb 26, 2026
33.5EM
6
Feb 26, 2026
75EM
6
Feb 26, 2026
0.44Latency (s)
6
Jun 30, 2026
52.07Bridge F1
6
Feb 26, 2026
36.3Answer F1
6
Feb 26, 2026
72.69Answer EM
6
Feb 26, 2026
15.2Exact Match Accuracy
6
Feb 26, 2026
70.33F1 Score
5
Jun 30, 2026
47.99F1 Score
5
Jun 30, 2026
8Indexing Time (min)
5
Jun 30, 2026
71.11Mean Accuracy
5
Jun 30, 2026
65.26Macro F1
5
Jun 15, 2026
58Accuracy
5
Jun 4, 2026
80.7Average Judge Score
5
May 27, 2026
62.3EM
5
May 27, 2026
70.8EM
5
May 27, 2026
62.2Correctness
5
May 20, 2026
73.4Performance (8K Context)
5
May 12, 2026